HH OpenClaw Agent

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:37 PM UTC
• Version:
  1.0.7

Overview

This skill is a coherent local helper for reviewed hh.ru job-application workflows, with disclosed browser-profile use and local packet/report file writes.

Review the packet before any live submission, use only an intended hh.ru browser profile, and avoid putting cookies, tokens, or secrets in notes or artifacts. The manifest may contain cover-letter and application details, so share the rendered report by default and use --include-sensitive only when you intentionally want full content exported.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence
• Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Missing User Warnings

Low

• Confidence: 83% confidence
• Finding: This code performs a file write that overwrites the manifest content, but there is no confirmation prompt or explicit warning comment/docstring explaining that the target file will be modified in place. The module docstring says it will append a step, but it does not clearly disclose that the existing JSON file is rewritten on disk.

VirusTotal

66/66 vendors flagged this skill as clean.